Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 60 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.7497. Min Act: -0.1700

Data Index: 4759704 (Open Web Text)

Max Activating Token Index: 75

Text #1

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.5988. Min Act: -0.1700

Data Index: 4077369 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.5901. Min Act: -0.1700

Data Index: 1569605 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.5687. Min Act: -0.1700

Data Index: 1490753 (Open Web Text)

Max Activating Token Index: 218

Text #4

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.4934. Min Act: -0.1700

Data Index: 650356 (Open Web Text)

Max Activating Token Index: 156

Text #5

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.4690. Min Act: -0.1700

Data Index: 771604 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.4721. Min Act: -0.1700

Data Index: 8013116 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.4696. Min Act: -0.1700

Data Index: 3355838 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.3947. Min Act: -0.1700

Data Index: 44785 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.3266. Min Act: -0.1700

Data Index: 3954410 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2997. Min Act: -0.1700

Data Index: 7646730 (Open Web Text)

Max Activating Token Index: 20

Text #11

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.3031. Min Act: -0.1700

Data Index: 7646737 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2559. Min Act: -0.1700

Data Index: 1025856 (Open Web Text)

Max Activating Token Index: 36

Text #13

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2917. Min Act: -0.1700

Data Index: 7135262 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2916. Min Act: -0.1700

Data Index: 4081544 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2598. Min Act: -0.1700

Data Index: 8392140 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2600. Min Act: -0.1700

Data Index: 144195 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2478. Min Act: -0.1700

Data Index: 8549600 (Open Web Text)

Max Activating Token Index: 440

Text #18

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2282. Min Act: -0.1700

Data Index: 6181899 (Open Web Text)

Max Activating Token Index: 40

Text #19

Max Range: 4.7497. Min Range: -4.7497

Max Act: 4.2214. Min Act: -0.1700

Data Index: 7646723 (Open Web Text)

Max Activating Token Index: 68